使用V-JEPA和深度时空学习的基于HPC的视频海岸波浪参数估计

中文摘要 AI 辅助

传统现场方法面临高部署成本、空间覆盖差和易受风暴条件影响等挑战。本文提出了一种基于视频和高性能计算（HPC）的深度学习框架，用于从单目海岸视频中联合无传感器估计五个海岸波浪参数，即有效波高（Hs）、最大波高（Hmax）、峰值周期（Tp）、零交叉周期（Tz）和波向（theta）。该框架包括用于在视觉挑战性场景中进行鲁棒时空特征提取的V-JEPA（自监督）ViT Small主干、用于在水动力破碎和涌浪状态下对波浪运动进行宽带宽表示的双流SlowFast时间编码器、基于Farneback光流算法的光流流以向结构添加显著性信息并强调波浪的水动力活跃波长带，以及具有色散约束（艾里波色散lambda_p = 0.1）的多任务回归层。该模型在NVIDIA DGX A100集群上进行训练，在第31个epoch提前停止，对于Hs、Hmax、Tp、Tz和波向分别实现了0.451、0.578、0.643、0.680和0.832的皮尔逊相关系数，对地理上不同的测试数据站点具有泛化能力。在数据有限的情况下（6个带注释的训练场景），该框架展示了统计学上显著的时间相关性（PCC为0.451至0.832），证实了概念验证的可行性；R2值（最大0.246）表明随着带注释数据集的增大，方差捕获将得到改善。

英文摘要

High deployment cost, poor spatial coverage and susceptibility to storm conditions are all challenges faced by traditional in-situ methods. This paper presents a video-based and high performance computing (HPC) enabled deep learning framework for joint sensor free estimation of five coastal wave parameters, namely significant wave height (Hs), maximum wave height (Hmax), peak period (Tp), zero upcrossing period (Tz) and wave direction (theta) from monocular coastal video. The proposed architecture comprises of a V-JEPA (self supervised) ViT Small backbone for robust spatiotemporal feature extraction in visually challenging scenarios, a dual-stream SlowFast temporal encoder for broad bandwidth representation of wave motion in both hydrodynamic breaking and swell regimes, an optical flow stream based on Farneback optical flow algorithm for adding saliency information to the structure with emphasis on hydrodynamically active wavelength bands of waves, and a multi-task regression layer with dispersion constraints (Airy wave dispersion lambda_p = 0.1). The model was trained on an NVIDIA DGX A100 cluster and was early stopped at epoch 31 and achieved Pearson correlation coefficients of 0.451, 0.578, 0.643, 0.680 and 0.832 for Hs, Hmax, Tp, Tz and wave direction respectively, with generalization ability to geographically diverse held out test data sites. While operating in a data-limited regime (6 annotated training scenes), the framework demonstrates statistically significant temporal correlations (PCC of 0.451 to 0.832), confirming proof of concept feasibility; R2 values (max 0.246) indicate that variance capture will improve with larger annotated datasets.

发表机构

• IEEE

机构由 AI 辅助整理，请以论文原文为准。